By Topic

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Issue 1 • Date Jan. 1985

Filter Results

Displaying Results 1 - 23 of 23
  • [Front cover]

    Page(s): c1
    Save to Project icon | Request Permissions | PDF file iconPDF (753 KB)  
    Freely Available from IEEE
  • List of Contributors

    Page(s): nil1
    Save to Project icon | Request Permissions | PDF file iconPDF (175 KB)  
    Freely Available from IEEE
  • [Breaker page]

    Page(s): nil1
    Save to Project icon | Request Permissions | PDF file iconPDF (175 KB)  
    Freely Available from IEEE
  • More About Polyhedra-Interpretation Through Constructions in the Image Plane

    Page(s): 1 - 16
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2910 KB)  

    This paper deals with the interpretation and feasibility check of line drawings representing polyhedral scenes. The polyhedra are of general types and there are no restrictions on camera position. The geometric consistency check and the line labeling are carried out through constructions in the image plane. An algorithm for the geometric construction is suggested, and the necessary conditions for these constructions are discussed. The image plane construction can be used for preparing labeled junction catalogs for junctions other than trihedral. In addition the paper analyzes the relation between the image plane construction and the gradient space construction suggested by Mackworth [7] for the same purpose. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computational Experiments with a Feature Based Stereo Algorithm

    Page(s): 17 - 34
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (11210 KB)  

    Computational models of the human stereo system can provide insight into general information processing constraints that apply to any stereo system, either artificial or biological. In 1977 Marr and Poggio proposed one such computational model, which was characterized as matching certain feature points in difference-of-Gaussian filtered images and using the information obtained by matching coarser resolution representations to restrict the search space for matching finer resolution representations. An implementation of the algorithm and its testing on a range of images was reported in 1980. Since then a number of psychophysical experiments have suggested possible refinements to the model and modifications to the algorithm. As well, recent computational experiments applying the algorithm to a variety of natural images, especially aerial photographs, have led to a number of modifications. In this paper, we present a version of the Marr-Poggio-Grimson algorithm that embodies these modifications, and we illustrate its performance on a series of natural images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Three-Dimensional Vision by Off-Shelf System with Multi-Cameras

    Page(s): 35 - 45
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4502 KB)  

    A three-dimnensional vision system for on-line operation that aids a collision avoidance system for an industrial robot is developed. Because of the real-time requirement, the process that locates and describes the obstacles must be fast. To satisfy the safety requirement, the obstacle model should always contain the physical obstacle entirely. This condition leads to the bounding box description of the obstacle, which is simple for the computer to process. The image processing is performed by a Machine Intelligence Corporation VS-100 machine vision system. The control and object perception is performed by the developed software on a host Digital Equipment Corporation VAX 11/780 Computer. The resultant system outputs a file of the locations and bounding descriptions for each object found. When the system is properly calibrated, the bounding descriptions always completely envelop the obstacle. The response time is data-dependent. When using two cameras and processed on UNIX time sharing mode, the average response time will be less than 2 s if eight or fewer objects are present. When using all three cameras, the average response time will be less than 4 s if eight or fewer objects are present. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image Normalization by Complex Moments

    Page(s): 46 - 55
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3548 KB)  

    The role of moments in image normalization and invariant pattern recognition is addressed. The classical idea of the principal axes is analyzed and extended to a more general definition. The relationship between moment-based normalization, moment invariants, and circular harmonics is established. Invariance properties of moments, as opposed to their recognition properties, are identified using a new class of normalization procedures. The application of moment-based normalization in pattern recognition is demonstrated by experiment. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel Algorithms for Syllable Recognition in Continuous Speech

    Page(s): 56 - 69
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3619 KB)  

    A distributed rule-based system for automatic speech recognition is described. Acoustic property extraction and feature hypothesization are performed by the application of sequences of operators. These sequences, called plans, are executed by cooperative expert programs. Experimental results on the automatic segmentation and recognition of phrases, made of connected letters and digits, are described and discussed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An Evaluation Based Theorem Prover

    Page(s): 70 - 79
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2243 KB)  

    A noninductive method for mechanical theorem proving is presented, which deals with a recursive class of theorems involving iterative functions and predicates. The method is based on the symbolic evaluation of the formula to be proved and requires no inductive step. Induction is avoided since a metatheorem is proved which establishes the conditions on the evaluation of any formula which are sufficient to assure that the formula actually holds. The proof of a supposed theorem consists in evaluating the formula and checking the conditions. The method applies to assertions that involve element-by-element checking of typed homogeneous sequences which are hierarchically constructed out of the primitive type consisting of the truth values. The sequences can be computed by means of iterative and ``accumulator'' functions. The paper includes the definition of a simple typed iterative language in which both predicates and functions are expressed. The language precisely defines the scope of the proof method. The method proves a wide variety of theorems about iterative functions on sequences, including that which states that REVERSE is its own inverse, and that it can be inversely distributed on APPEND, that FLATTEN can be distributed on APPEND and that each element of any sequence is a MEMBER of the sequence itself. Although the method is not complete, it does provide the basis for an extremely efficient tool to be used in a complete mechanical theorem prover. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A VLSI Systolic Architecture for Pattern Clustering

    Page(s): 80 - 89
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2645 KB)  

    Cluster analysis is a valuable tool in exploratory pattern analysis, especially when very little prior information about the data is available. In unsupervised pattern recognition and image segmentation applications, clustering techniques play an important role. The squared-error clustering technique is the most popular one among different clustering techniques. Due to the iterative nature of the squared-error clustering, it demands substantial CPU time, even for modest numbers of patterns. Recent advances in VLSI microelectronic technology triggered the idea of implementing the squared-error clustering directly in hardware. A two-level pipelined systolic pattern clustering array is proposed in this paper. The memory storage and access schemes are designed to enable a rhythmic data flow between processing units. Each processing unit is pipelined to further enhance the system performance. The total processing time for each pass of pattern labeling and cluster center updating is essentially dominated by the time required to fetch the pattern matrix once. Detailed architectural configuration, system performance evaluation, and simulation experiments are presented. The modularity and the regularity of the system architecture make it suited for VLSI implementations. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Metric for Comparing Relational Descriptions

    Page(s): 90 - 94
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1026 KB)  

    Relational models are frequently used in high-level computer vision. Finding a correspondence between a relational model and an image description is an important operation in the analysis of scenes. In this paper the process of finding the correspondence is formalized by defining a general relational distance measure that computes a numeric distance between any two relational descriptions-a model and an image description, two models, or two image descriptions. The distance measure is proved to be a metric, and is illustrated with examples of distance between object models. A variant measure used in our past studies is shown not to be a metric. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Top-Down Quadtree Traversal Algorithm

    Page(s): 94 - 98
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1214 KB)  

    Many standard image processing operations can be implemented using quadtrees as a simple tree traversal where, at each terminal node, a computation is performed involving some of that node's neighbors. Most of this work has involved the use of bottom-up neighbor-finding techniques which search for a nearest common ancestor. Recently, top-down techniques have been proposed which make use of a neighbor vector as the tree is traversed. A simplified version of the top-down method for a quadtree in the context of a general-purpose tree traversal algorithm is presented. It differs, in part, from prior work in its ability to compute diagonally adjacent neighbors rather than just horizontally and vertically adjacent neighbors. It builds a neighbor vector for each node using a minimal amount of information. Analysis of the algorithm shows that its execution time is directly proportional to the number of nodes in the tree. However, it does require some extra storage. Use of the algorithm leads to lower execution time bounds for some common quadtree image processing operations such as connected component labeling. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fourier Encoding of Closed Planar Boundaries

    Page(s): 98 - 102
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1035 KB)  

    A circular Gaussian autoregressive (CGAR) source is used as a model for closed planar curves. A class of suboptimal encoding schemes is considered which separately quantize the Fourier coefficients of the boundary. Application of rate-distortion theoretic techniques leads to parametric equations describing the optimal encoding bound. Interpretation of these equations establishes a sampling criterion and a computationally efficient transform encoding scheme for the suboptimal class. Several variants of this transform encoding scheme are suggested and compared to the encoding bound. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A New Heuristic Search Technique-Algorithm SA

    Page(s): 103 - 107
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (878 KB)  

    In this paper, we present a new heuristic searching algorithm by introducing the statistical inference method on the basis of algorithm A (or A*). It is called algorithm SA. In a simplified search space, a uniform m-ary tree, we obtain the following result. Using algorithm SA, a goal node can be found with probability one, and its mean complexity is O(N·ln N) where N is the depth at which the goal is located. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The 2-NN Rule for More Accurate NN Risk Estimation

    Page(s): 107 - 112
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1114 KB)  

    By proper design of a nearest-neighbor (NN) rule, it is possible to reduce effects of sample size in NN risk estimation. The 2-NN rule for the two-class problem eliminates the first-order effects of sample size. Since its asymptotic value is exactly half that of the 1-NN rule, it is possible to substitute the 2-NN rule for the 1-NN rule with a resultant increase in accuracy. For further stabilization of the risk estimate with respect to sample size, 2-NN polarization is suggested. Examples are included. The 2-NN approach is extended to M-class and 2k-NN. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The Separating Capacity of a Multithreshold Threshold Element

    Page(s): 112 - 116
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (927 KB)  

    In answer to what represents the intrinsic information-processing capability of the pattern classification system, Cover [1] has defined the separating capacity, and has derived it for the linear machine and the so-called ¿ machine. In this paper, the separating capacity of a multithreshold classification element is obtained. It is shown that the capacity of a multithreshold threshold element with k thresholds-k-threshold element-in n-dimensional space is 2(n + k). A linear machine is a special case in the k-threshold element with k = 1; therefore, its capacity becomes 2(n + 1) from the above result. Further, although it is intuitively apparent that the larger the number of thresholds, the more powerful the information-processing capability of the k-threshold element, using the capacity as a measure of this capability, we may now state that the separating power of the k-threshold element increases linearly with respect to k. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Handling Memory Overflow in Connected Component Labeling Applications

    Page(s): 116 - 121
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1257 KB)  

    The storage requirements for component labeling and feature extraction operations are unknown a priori. Whenever large images are processed, many labels, and thus a large amount of storage, may be required, making hardware implementation difficult. The proposed labeling procedure eliminates memory overflow by enabling the reuse of memory locations in which features of nonactive labels had been stored. The storage requirement for the worst case conditions is analyzed and is shown to be realizable. The basic procedure can be implemented in two modes, an interrupted mode or a parallel mode. A hardware design is presented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Comments on "Digital Step Edges from Zero Crossings of Second Directional Derivatives

    Page(s): 121 - 127
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2949 KB)  

    In a recent paper,1 Haralick published an edge detection scheme that was supported, in part, by an evaluation against the Prewitt and the Marr-Hildreth (??2G) operators. This evaluation led to the conclusion that Haralick's method performed the best, and the ??2G operator performed the worst. The implementation of the ??2G operator, on which this evaluation was based, differed significantly from that used by Marr and Hildreth. Evaluation of the performance of the Marr-Hildreth implementation of the ??2G operator on similar images shows that this edge detection method in fact performs comparably to the Prewitt and Haralick operators. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Author's Reply

    Page(s): 127 - 129
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2630 KB)  

    We present evidence that the Laplacian zero-crossing operator does not use neighborhood information as effectively as the second directional derivative edge operator. We show that the use of a Gaussian smoother with standard deviation 5.0 for the Laplacian of a Gaussian edge operator with a neighborhood size of 50 × 50 both misses and misplaces edges on an aerial image of a mobile home park. Contrary to Grimson and Hildreth's results, our results of the Laplacian edge detector on a noisy test checkerboard image are also not as good as the second directional derivative edge operator. We conclude by discussing a number of open issues on edge operator evaluation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Information for authors

    Page(s): 130
    Save to Project icon | Request Permissions | PDF file iconPDF (234 KB)  
    Freely Available from IEEE
  • [Breaker page]

    Page(s): 131 - 132
    Save to Project icon | Request Permissions | PDF file iconPDF (268 KB)  
    Freely Available from IEEE
  • List of Contributors

    Page(s): nil2
    Save to Project icon | Request Permissions | PDF file iconPDF (187 KB)  
    Freely Available from IEEE
  • [Front cover]

    Page(s): c2
    Save to Project icon | Request Permissions | PDF file iconPDF (160 KB)  
    Freely Available from IEEE

Aims & Scope

The IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) is published monthly. Its editorial board strives to present most important research results in areas within TPAMI's scope.

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
David A. Forsyth
University of Illinois